Using Convolutional Neural Networks to Detect Copper and Zinc Contamination through Cell Images of Egeria densa Leaf
- 1National Taipei University of Technology , , No.1, Sec. 3, Zhongxiao E. Road , ,
Abstract
Bioassays offer sensitive and cost-effective methods for detecting heavy metal contamination. In this study, we further integrate convolutional neural networks (CNNs) into bioassays, enabling high-throughput analysis. Specifically, we detect copper or zinc contamination through cell images of Egeria densa leaves. Four CNN models (InceptionV3, EfficientNetB1, ResNet152, and DenseNet121) achieved an accuracy of 99% in distinguishing among 0 ppm (control), 0.1 ppm copper, and 0.1 ppm zinc contamination. Other metrics, including precision, recall, and F1-score, all reached 0.99. Furthermore, when classifying three concentrations (0, 0.1, and 0.5 ppm) of copper or zinc contamination, ResNet152 achieved an accuracy of 98.4% for copper and 98.3% for zinc, and all models achieved an accuracy of over 93%, demonstrating their ability to distinguish between contamination severities. The results suggest that the combination of CNN with bioassays has the potential to monitor heavy metal contamination in the environment.
Related
- Site-Selective Functional Group Classification of Auger-Electron Spectra and Core-Electron Binding Energies with Convolutional Neural Networks
- Predicting Adsorbate-Solvent Interaction Energies in Zeolite Pores Using Convolutional Neural Networks with Attention Mechanisms.
- Carbon Nanotube-Induced Magnetic Shielding Effects on 129Xe NMR from Equivariant Neural Networks
- Site-Resolved Prediction of Mayr Nucleophilicity with Reactivity-Pretrained Graph Neural Networks
- Thermodynamically informed and balance-preserving neural networks for direct vapor–liquid flash calculations
BibTeX
@article{tseng2026using,
title = {{Using Convolutional Neural Networks to Detect Copper and Zinc Contamination through Cell Images of Egeria densa Leaf}},
author = {Ching-Jui Tseng and Chen-Chen Wang and Chung-Heng Liu and You-Chen Gou and Che-Chi Shu},
journal = {ACS Omega},
year = {2026},
month = nov,
doi = {10.1021/acsomega.6c02216},
url = {https://pubs.acs.org/acsodf/article/doi/10.1021/acsomega.6c02216/5466440/Using-Convolutional-Neural-Networks-to-Detect},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Using Convolutional Neural Networks to Detect Copper and Zinc Contamination through Cell Images of Egeria densa Leaf
AU - Ching-Jui Tseng
AU - Chen-Chen Wang
AU - Chung-Heng Liu
AU - You-Chen Gou
AU - Che-Chi Shu
PY - 2026
DA - 2026/11/09
JO - ACS Omega
DO - 10.1021/acsomega.6c02216
UR - https://pubs.acs.org/acsodf/article/doi/10.1021/acsomega.6c02216/5466440/Using-Convolutional-Neural-Networks-to-Detect
AB - Bioassays offer sensitive and cost-effective methods for detecting heavy metal contamination. In this study, we further integrate convolutional neural networks (CNNs) into bioassays, enabling high-throughput analysis. Specifically, we detect copper or zinc contamination through cell images of Egeria densa leaves. Four CNN models (InceptionV3, EfficientNetB1, ResNet152, and DenseNet121) achieved an accuracy of 99% in distinguishing among 0 ppm (control), 0.1 ppm copper, and 0.1 ppm zinc contamination. Other metrics, including precision, recall, and F1-score, all reached 0.99. Furthermore, when classifying three concentrations (0, 0.1, and 0.5 ppm) of copper or zinc contamination, ResNet152 achieved an accuracy of 98.4% for copper and 98.3% for zinc, and all models achieved an accuracy of over 93%, demonstrating their ability to distinguish between contamination severities. The results suggest that the combination of CNN with bioassays has the potential to monitor heavy metal contamination in the environment.
SN - 2470-1343
ER -